Triple
T38637092
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Microsoft Ignite 2021 |
E937593
|
entity |
| Predicate | hasKeynoteBy |
P113003
|
FINISHED |
| Object | Satya Nadella |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Satya Nadella | Statement: [Microsoft Ignite 2021, hasKeynoteBy, Satya Nadella]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasKeynoteBy Context triple: [Microsoft Ignite 2021, hasKeynoteBy, Satya Nadella]
-
A.
hasKeynoteDate
Indicates the date on which a keynote event or keynote speech is scheduled or occurs.
-
B.
hasKeyNote
Indicates that one entity serves as the primary or central theme, idea, or focus (the keynote) associated with another entity.
-
C.
hasNotableSpeaker
chosen
Indicates that an event, gathering, or occasion features a speaker who is distinguished or noteworthy in some significant way.
-
D.
hasSpeakersIn
Indicates that an entity (such as an event, conference, or session) includes or is associated with speakers located in or belonging to a specified place or group.
-
E.
hasSpeakersAmong
Indicates that a group, event, or entity includes one or more speakers drawn from a specified set or category.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f76ed5ca3c81909288f61fbf37b359 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd68abf52881909c5a390c362b7c59 |
completed | May 8, 2026, 4:38 a.m. |
| PD | Predicate disambiguation | batch_69fd6812d0c88190930d8fa2d4b92490 |
completed | May 8, 2026, 4:35 a.m. |
Created at: May 3, 2026, 4:32 p.m.